PIPENN: protein interface prediction from sequence with an ensemble of neural nets.

MOTIVATION: The interactions between proteins and other molecules are essential to many biological and cellular processes. Experimental identification of interface residues is a time-consuming, costly and challenging task, while protein sequence data are ubiquitous. Consequently, many computational and machine learning approaches have been developed over the years to predict such interface residues from sequence. However, the effectiveness of different Deep Learning (DL) architectures and learning strategies for protein-protein, protein-nucleotide and protein-small molecule interface prediction has not yet been investigated in great detail. Therefore, we here explore the prediction of protein interface residues using six DL architectures and various learning strategies with sequence-derived input features. RESULTS: We constructed a large dataset dubbed BioDL, comprising protein-protein interactions from the PDB, and DNA/RNA and small molecule interactions from the BioLip database. We also constructed six DL architectures, and evaluated them on the BioDL benchmarks. This shows that no single architecture performs best on all instances. An ensemble architecture, which combines all six architectures, does consistently achieve peak prediction accuracy. We confirmed these results on the published benchmark set by Zhang and Kurgan (ZK448), and on our own existing curated homo- and heteromeric protein interaction dataset. Our PIPENN sequence-based ensemble predictor outperforms current state-of-the-art sequence-based protein interface predictors on ZK448 on all interaction types, achieving an AUC-ROC of 0.718 for protein-protein, 0.823 for protein-nucleotide and 0.842 for protein-small molecule. AVAILABILITY AND IMPLEMENTATION: Source code and datasets are available at https://github.com/ibivu/pipenn/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SeRenDIP-CE: sequence-based interface prediction for conformational epitopes.

MOTIVATION: Antibodies play an important role in clinical research and biotechnology, with their specificity determined by the interaction with the antigen's epitope region, as a special type of protein-protein interaction (PPI) interface. The ubiquitous availability of sequence data, allows us to predict epitopes from sequence in order to focus time-consuming wet-lab experiments toward the most promising epitope regions. Here, we extend our previously developed sequence-based predictors for homodimer and heterodimer PPI interfaces to predict epitope residues that have the potential to bind an antibody. RESULTS: We collected and curated a high quality epitope dataset from the SAbDab database. Our generic PPI heterodimer predictor obtained an AUC-ROC of 0.666 when evaluated on the epitope test set. We then trained a random forest model specifically on the epitope dataset, reaching AUC 0.694. Further training on the combined heterodimer and epitope datasets, improves our final predictor to AUC 0.703 on the epitope test set. This is better than the best state-of-the-art sequence-based epitope predictor BepiPred-2.0. On one solved antibody-antigen structure of the COVID19 virus spike receptor binding domain, our predictor reaches AUC 0.778. We added the SeRenDIP-CE Conformational Epitope predictors to our webserver, which is simple to use and only requires a single antigen sequence as input, which will help make the method immediately applicable in a wide range of biomedical and biomolecular research. AVAILABILITY AND IMPLEMENTATION: Webserver, source code and datasets at www.ibi.vu.nl/programs/serendipwww/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Systematically linking tranSMART, Galaxy and EGA for reusing human translational research data.

The availability of high-throughput molecular profiling techniques has provided more accurate and informative data for regular clinical studies. Nevertheless, complex computational workflows are required to interpret these data. Over the past years, the data volume has been growing explosively, requiring robust human data management to organise and integrate the data efficiently. For this reason, we set up an ELIXIR implementation study, together with the Translational research IT (TraIT) programme, to design a data ecosystem that is able to link raw and interpreted data. In this project, the data from the TraIT Cell Line Use Case (TraIT-CLUC) are used as a test case for this system. Within this ecosystem, we use the European Genome-phenome Archive (EGA) to store raw molecular profiling data; tranSMART to collect interpreted molecular profiling data and clinical data for corresponding samples; and Galaxy to store, run and manage the computational workflows. We can integrate these data by linking their repositories systematically. To showcase our design, we have structured the TraIT-CLUC data, which contain a variety of molecular profiling data types, for storage in both tranSMART and EGA. The metadata provided allows referencing between tranSMART and EGA, fulfilling the cycle of data submission and discovery; we have also designed a data flow from EGA to Galaxy, enabling reanalysis of the raw data in Galaxy. In this way, users can select patient cohorts in tranSMART, trace them back to the raw data and perform (re)analysis in Galaxy. Our conclusion is that the majority of metadata does not necessarily need to be stored (redundantly) in both databases, but that instead FAIR persistent identifiers should be available for well-defined data ontology levels: study, data access committee, physical sample, data sample and raw data file. This approach will pave the way for the stable linkage and reuse of data.